{"id":"W3173233968","doi":"10.1109/tip.2021.3088266","title":"Blind Decomposition of Multispectral Document Images Using Orthogonal Nonnegative Matrix Factorization","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Blind Source Separation Techniques","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Orthogonality; Multispectral image; Matrix decomposition; Endmember; Hyperspectral imaging; Computer science; Non-negative matrix factorization; Pattern recognition (psychology); Artificial intelligence; Generalization; Mathematics; Algorithm","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001902197,0.0001765064,0.0001946495,0.0002471545,0.0002748638,0.0003385964,0.0002155288,0.00008072375,0.00003682872],"category_scores_gemma":[0.000008912511,0.0001900643,0.0001030223,0.0007227347,0.00006823635,0.00193658,0.000005046319,0.0002323624,0.000005115148],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001155704,"about_ca_system_score_gemma":0.0002873602,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001445321,"about_ca_topic_score_gemma":0.00001043686,"domain_scores_codex":[0.9985107,0.0001392466,0.0003916175,0.0003937006,0.0003639128,0.0002007809],"domain_scores_gemma":[0.9989039,0.00007058863,0.0002235068,0.0002474641,0.0004905555,0.00006398791],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0000526551,0.0004389612,0.00001821287,0.0001100819,0.00004158606,0.0000206275,0.002829436,0.01253447,0.9362308,0.0009295325,0.000008714715,0.04678493],"study_design_scores_gemma":[0.000457488,0.00005632627,0.00008479122,0.0001161442,0.00002319115,0.00003888808,0.00008655876,0.08920987,0.9080189,0.001722165,0.000006905333,0.0001787231],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03076371,0.0000631278,0.9682031,0.000250569,0.0001487049,0.0001760622,0.00001355793,0.0002188344,0.0001622885],"genre_scores_gemma":[0.6063227,0.00001173929,0.3935377,0.00004407361,0.00001513228,0.00001051063,0.000003977455,0.00001117641,0.00004300952],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.575559,"threshold_uncertainty_score":0.7750599,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01956661895833868,"score_gpt":0.3388252237122917,"score_spread":0.3192586047539531,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}